{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AKZVM2KT63CKFSYK4LJOJFDG7R","short_pith_number":"pith:AKZVM2KT","schema_version":"1.0","canonical_sha256":"02b3566953f6c4a2cb0ae2d2e49466fc44532c6d17d7d7d357e5d2b049e46337","source":{"kind":"arxiv","id":"2605.15899","version":1},"attestation_state":"computed","paper":{"title":"Solving Classical and Quantum Spin Glasses with Deep Boltzmann Quantum States","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Deep Boltzmann Quantum States solve large classical and quantum spin glasses by matching exact or best-known ground states.","cross_cats":["quant-ph"],"primary_cat":"cond-mat.dis-nn","authors_text":"Arka Dutta, Enrico Prati, Luca Leone, Markus Heyl, Pietro Torta","submitted_at":"2026-05-15T12:30:07Z","abstract_excerpt":"Variational neural network models have achieved remarkable success in solving ground-state problems of quantum many-body systems. However, addressing classical and quantum spin glasses remains challenging, as disorder and energy frustration give rise to an exponentially large number of local energy minima separated by high-energy barriers, hindering the efficiency of conventional Metropolis-based Monte Carlo methods. To bridge this gap, we introduce Deep Boltzmann Quantum States, a class of neural quantum states inspired by deep Boltzmann machines that inherit efficient block Gibbs sampling. W"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.15899","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2026-05-15T12:30:07Z","cross_cats_sorted":["quant-ph"],"title_canon_sha256":"d34f5ee3b916bab9495c115bc2cc197a7d5dc2493f9207f8ca720cd9835a8bd4","abstract_canon_sha256":"fdf96e956d077e5f48d5c9d1489c99105fe88fe5dbcb460d134781815b670569"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:24.466130Z","signature_b64":"t6LFkJahkks3kBxPk9XPkaquqX54MwXJMjy95U72zqO7Uy/r3dghUcn4uelYwiB+ahSBZzg7QbraTDV+n0TWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02b3566953f6c4a2cb0ae2d2e49466fc44532c6d17d7d7d357e5d2b049e46337","last_reissued_at":"2026-05-20T00:01:24.465306Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:24.465306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Classical and Quantum Spin Glasses with Deep Boltzmann Quantum States","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Deep Boltzmann Quantum States solve large classical and quantum spin glasses by matching exact or best-known ground states.","cross_cats":["quant-ph"],"primary_cat":"cond-mat.dis-nn","authors_text":"Arka Dutta, Enrico Prati, Luca Leone, Markus Heyl, Pietro Torta","submitted_at":"2026-05-15T12:30:07Z","abstract_excerpt":"Variational neural network models have achieved remarkable success in solving ground-state problems of quantum many-body systems. However, addressing classical and quantum spin glasses remains challenging, as disorder and energy frustration give rise to an exponentially large number of local energy minima separated by high-energy barriers, hindering the efficiency of conventional Metropolis-based Monte Carlo methods. To bridge this gap, we introduce Deep Boltzmann Quantum States, a class of neural quantum states inspired by deep Boltzmann machines that inherit efficient block Gibbs sampling. W"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We match the exact solution or the best available estimate for several instances of classical and quantum Ising spin-glass models with infinite-range interactions and hundreds of spins. We also solve instances of the NP-hard Job Shop Scheduling Problem exceeding the current limitations of quantum annealing hardware.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The neural network ansatz combined with block Gibbs sampling and the hardness-interpolation schedule is expressive enough to reach the global ground state without becoming trapped in the exponentially many local minima characteristic of spin glasses, even when the instantaneous adiabatic state is not closely tracked at intermediate hardness values.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Deep Boltzmann Quantum States with natural-gradient optimization and annealing-like training match exact or best-known solutions for large infinite-range Ising spin glasses and solve job shop scheduling instances.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Deep Boltzmann Quantum States solve large classical and quantum spin glasses by matching exact or best-known ground states.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"775cc31e7cef8c3a3e05224a8626cd2a6ce7caa101cd826e308bb9dfbd7ab46d"},"source":{"id":"2605.15899","kind":"arxiv","version":1},"verdict":{"id":"96addae9-d28f-487b-bea0-d1270cbf291b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:52:00.568346Z","strongest_claim":"We match the exact solution or the best available estimate for several instances of classical and quantum Ising spin-glass models with infinite-range interactions and hundreds of spins. We also solve instances of the NP-hard Job Shop Scheduling Problem exceeding the current limitations of quantum annealing hardware.","one_line_summary":"Deep Boltzmann Quantum States with natural-gradient optimization and annealing-like training match exact or best-known solutions for large infinite-range Ising spin glasses and solve job shop scheduling instances.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The neural network ansatz combined with block Gibbs sampling and the hardness-interpolation schedule is expressive enough to reach the global ground state without becoming trapped in the exponentially many local minima characteristic of spin glasses, even when the instantaneous adiabatic state is not closely tracked at intermediate hardness values.","pith_extraction_headline":"Deep Boltzmann Quantum States solve large classical and quantum spin glasses by matching exact or best-known ground states."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15899/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T18:01:18.569075Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:01:11.474855Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:46.565921Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.774503Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"cfcb638e3a6fac523ddf3a85d4f412f49ce9895e459ce7f57fd5ec118fb63fe3"},"references":{"count":145,"sample":[{"doi":"","year":null,"title":"A noteworthy observation is that imaginary-time TDVP is formally equivalent to the optimization of the cost func- tion in Eq","work_id":"0d6fa84f-14bf-4c43-a9c9-a7680e5f5339","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The resulting high-level im- plementation of VQA for optimizing a variational ansatz (typically an NQS) is illustrated in Algorithm 2","work_id":"2827eb90-fcb4-410b-b538-516d491de8a2","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"[123] and known as pmRBM uses two independent RBMs to model the phase and the modulus of the wave- function","work_id":"accb295b-8015-4cc8-86cc-02816d01fdc4","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"DBM wavefunctions A possible quantum extension of DBMs based on the same principle of the cRBM was introduced in Ref. [32] and reads ψ(x;θ)= X x(l) l>0 e PNL −1 l=0 x(l)T W (l)x(l+1)+PNL l=0 b(l)T x(l","work_id":"0be2ec2e-c332-4ec9-9ab4-932a89d42901","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Quantum Boltzmann Machines Another possible extension, dubbed Quantum Boltz- mann Machine (QBM), was proposed in Ref. [122]. The units of the BM are promoted to quantum spins, and the state of the sys","work_id":"862694c3-fd00-4687-96f0-02269e394d31","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":145,"snapshot_sha256":"f6cb5b7dcfed7ab50111fa5dad697d23bb55caa177c2bbd131c6aa80376e9b6f","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"848c197ed149f9afe317877574b5e93b7a8cfef262824347adab63b25445d10b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.15899","created_at":"2026-05-20T00:01:24.465465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15899v1","created_at":"2026-05-20T00:01:24.465465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15899","created_at":"2026-05-20T00:01:24.465465+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKZVM2KT63CK","created_at":"2026-05-20T00:01:24.465465+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKZVM2KT63CKFSYK","created_at":"2026-05-20T00:01:24.465465+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKZVM2KT","created_at":"2026-05-20T00:01:24.465465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AKZVM2KT63CKFSYK4LJOJFDG7R","json":"https://pith.science/pith/AKZVM2KT63CKFSYK4LJOJFDG7R.json","graph_json":"https://pith.science/api/pith-number/AKZVM2KT63CKFSYK4LJOJFDG7R/graph.json","events_json":"https://pith.science/api/pith-number/AKZVM2KT63CKFSYK4LJOJFDG7R/events.json","paper":"https://pith.science/paper/AKZVM2KT"},"agent_actions":{"view_html":"https://pith.science/pith/AKZVM2KT63CKFSYK4LJOJFDG7R","download_json":"https://pith.science/pith/AKZVM2KT63CKFSYK4LJOJFDG7R.json","view_paper":"https://pith.science/paper/AKZVM2KT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15899&json=true","fetch_graph":"https://pith.science/api/pith-number/AKZVM2KT63CKFSYK4LJOJFDG7R/graph.json","fetch_events":"https://pith.science/api/pith-number/AKZVM2KT63CKFSYK4LJOJFDG7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKZVM2KT63CKFSYK4LJOJFDG7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKZVM2KT63CKFSYK4LJOJFDG7R/action/storage_attestation","attest_author":"https://pith.science/pith/AKZVM2KT63CKFSYK4LJOJFDG7R/action/author_attestation","sign_citation":"https://pith.science/pith/AKZVM2KT63CKFSYK4LJOJFDG7R/action/citation_signature","submit_replication":"https://pith.science/pith/AKZVM2KT63CKFSYK4LJOJFDG7R/action/replication_record"}},"created_at":"2026-05-20T00:01:24.465465+00:00","updated_at":"2026-05-20T00:01:24.465465+00:00"}